Abstract: Systems and methods are provided to implement intelligent recommendations to users by modeling user profiles through deep learning of multimodal user data. For example, a recommendation computing platform collects multimodal user data from a computing device of a registered user, wherein the multimodal user data include time-series data, unstructured textual data, and multimedia data. A first deep learning classification engine is utilized to extract features from the multimodal user data. A second deep learning classification engine is utilized to generate a profile of the registered user based on the extracted features. A deep recommendation classification engine is utilized to determine a recommendation for the registered user based on the profile of the registered user, wherein the recommendation identifies at least one additional registered user. The recommendation is presented to the registered user on the computing device of the registered user.

Abstract: One embodiment provides a method, including: receiving a natural language query; selecting a disambiguation state model representing conversational dialogue history, wherein the disambiguation state model comprises a plurality of nodes representing an entity, and a plurality of edges representing a path between two of the plurality of nodes, each of the plurality of edges including an assigned weight; traversing, the disambiguation state model using the natural language query to select a path to one of the plurality of nodes and providing the user the entity associated with the one of the plurality of nodes and iteratively selecting paths and nodes based upon input received from the user until a final node of the disambiguation state model is reached; providing a response to the natural language query based upon the entity of the final node; and updating the disambiguation state model based upon the traversed paths and nodes.

Abstract: Methods, systems, and computer program products for multi-modal construction of deep learning networks are provided herein. A computer-implemented method includes extracting, from user-provided multi-modal inputs, one or more items related to generating a deep learning network; generating a deep learning network model, wherein said generating comprises inferring multiple details attributed to the deep learning network model based on the one or more extracted items; creating an intermediate representation based on the deep learning network model, wherein the intermediate representation comprises (i) one or more items of data pertaining to the deep learning network model and (ii) one or more design details attributed to the deep learning network model; automatically converting the intermediate representation into source code; and outputting the source code to at least one user.

Abstract: One embodiment provides a method for generating a process learning graph and a document output from a recorded process for training a cognitive agent, the method comprising: utilizing at least one processor to execute computer code that performs the steps of: obtaining a recording of a process, wherein the recording comprises a demonstration of executing the process; generating, using the recording, the process learning graph, wherein the process learning graph identifies a process flow; generating, using the recording, the document output, wherein the document output comprises process screen transitions and process steps; and providing the process learning graph and the document output to the cognitive agent. Other aspects are described and claimed.

Abstract: One embodiment provides a method for generating a process learning graph and a document output from a recorded process for training a cognitive agent, the method comprising: utilizing at least one processor to execute computer code that performs the steps of: obtaining a recording of a process, wherein the recording comprises a demonstration of executing the process; generating, using the recording, the process learning graph, wherein the process learning graph identifies a process flow; generating, using the recording, the document output, wherein the document output comprises process screen transitions and process steps; and providing the process learning graph and the document output to the cognitive agent. Other aspects are described and claimed.